ARXIV:2603.15546 · HUMAN MOTION GENERATION · SUBMITTED 18 MAR · 22:54 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: partial proof status

Kimodo: Scaling Controllable Human Motion Generation

Q: What products could be built from this research?

Now is the ideal time because demand for realistic digital humans is surging in gaming, metaverse applications, and AI-driven robotics, while advances in diffusion models and increased availability of large-scale mocap data make this technically feasible. The market is ripe for tools that bridge the gap between high cost and scalability, especially as industries push for more immersive and interactive content.

Q: What are the practical use cases?

A video game studio uses the product to generate realistic NPC animations for an open-world game, inputting text prompts like 'sneaking through a forest' or kinematic constraints for specific combat moves, reducing animation production time by 70% compared to manual keyframing or limited mocap libraries.

arXiv

Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

Blocked on Code›Score7.0Evidence partial

Opportunity summary

Pain Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

Evidence 0 refs | 0 sources | 50% coverage

Blocker Evidence partial

Open Build Read PDF Signal Canvas Track

PROBLEM

Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or…

METHOD

Full abstract

High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or kinematic constraints on poses. However, the small scale of public mocap datasets has limited the motion quality, control accuracy, and generalization of these models. In this work, we introduce Kimodo, an expressive and controllable kinematic motion diffusion model trained on 700 hours of optical motion capture data. Our model generates high-quality motions while being easily controlled through text and a comprehensive suite of kinematic constraints including full-body keyframes, sparse joint positions/rotations, 2D waypoints, and dense 2D paths. This is enabled through a carefully designed motion representation and two-stage denoiser architecture that decomposes root and body prediction to minimize motion artifacts while allowing for flexible constraint conditioning. Experiments on the large-scale mocap dataset justify key design decisions and analyze how the scaling of dataset size and model size affect performance.

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. Experiments on the large-scale mocap dataset justify key design decisions and analyze how the scaling of dataset size and model size affect performance. A…

WHY NOW

Human Motion Generation moved forward this cycle; last verified April 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score7.0

PainKimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

Evidence0 refs | 0 sources | 50% coverage

Blockermissing authors

Analysis summary

Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: partial proof status

ARXIV:2603.15546 · HUMAN MOTION GENERATION · SUBMITTED 18 MAR · 22:54 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: partial proof status

Kimodo: Scaling Controllable Human Motion Generation

arXiv

Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

Blocked on Code›Score7.0Evidence partial

Opportunity summary

Pain Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

Evidence 0 refs | 0 sources | 50% coverage

Blocker Evidence partial

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

WHY NOW

Human Motion Generation moved forward this cycle; last verified April 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score7.0

PainKimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

Evidence0 refs | 0 sources | 50% coverage

Blockermissing authors

Analysis summary

Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: partial proof status

Paper Pack

10.48550/arXiv.2603.15546

Kimodo: Scaling Controllable Human Motion Generation

Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

partial

0 refs; 0 sources; 50% coverage.

What was readable

linkedon filenot materializedderived fallback49 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

7.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

WHY NOW

Human Motion Generation moved forward this cycle; last verified April 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or kinematic constraints on poses.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data source, enabling human motion synthesis through intuitive inputs like text prompts or kinematic constraints on poses.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 7.0/10 on the public viability pass. Experiments on the large-scale mocap dataset justify key design decisions and analyze how the scaling of dataset size and model size affect performance. A public repository is linked, so build verification can inspect implementation evidence instead of treating the paper as PDF-only.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Human Motion Generation moved forward this cycle; last verified April 2026. Public score 7.0/10. Implementation evidence is present through a linked repository.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Human Motion Generation

Competitors

not indexed

Competitive landscape

Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.

Segment

Human Motion Generation

Adoption evidence

Public code linked for build inspection

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2603.15546 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(49)

HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation

2025Yuxin Wen, Qing Shuai et al.

MaskedManipulator: Versatile Whole-Body Control for Loco-Manipulation

2025Chen Tessler, Yifeng Jiang et al.

SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control

2025Zhengyi Luo, Ye Yuan et al.

The Quest for Generalizable Motion Generation: Data, Model, and Evaluation

2025Jing Lin, Ruisi Wang et al.

Viser: Imperative, Web-based 3D Visualization in Python

2025Brent Yi, Chung Min Kim et al.

Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

2025Ke Fan, Shunlin Lu et al.

Absolute Coordinates Make Motion Generation Easy

2025Zichong Meng, Zeyu Han et al.

TWIST: Teleoperated Whole-Body Imitation System

2025Yanjie Ze, Zixuan Chen et al.

GENMO: A GENeralist Model for Human MOtion

2025Jiefeng Li, Jinkun Cao et al.

Motion Synthesis with Sparse and Flexible Keyjoint Control

2025I. Hwang, Jinseok Bae et al.

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model

2024Shunlin Lu, Jingbo Wang et al.

MaskControl: Spatio-Temporal Control for Masked Motion Synthesis

2024Ekkasit Pinyoanuntapong, Muhammad Usama Saleem et al.

DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

2024Kaifeng Zhao, Gen Li et al.

MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting

2024Chen Tessler, Yunrong Guo et al.

Scaling Exponents Across Parameterizations and Optimizers

2024Katie Everett, Lechao Xiao et al.

Flexible Motion In-betweening with Diffusion Models

2024S. Cohan, Guy Tevet et al.

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

2024Parishad BehnamGhader, Vaibhav Adlakha et al.

Large Motion Model for Unified Multi-Modal Motion Generation

2024Mingyuan Zhang, Daisheng Jin et al.

MMM: Generative Masked Motion Model

2023Ekkasit Pinyoanuntapong, Pu Wang et al.

MoMask: Generative Masked Modeling of 3D Human Motions

2023Chuan Guo, Yuxuan Mu et al.

Showing 20 of 49 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkAnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

7.0

Prior WorkBridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

7.0

Prior WorkKinodynamic Motion Retargeting for Humanoid Locomotion via Multi-Contact Whole-Body Trajectory Optimization

7.0

Prior WorkPhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization

7.0

Prior WorkLearning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregation

7.0

Prior WorkCoordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation

7.0

Prior WorkSketch2Colab: Sketch-Conditioned Multi-Human Animation via Controllable Flow Distillation

7.0

Prior WorkSPARK: Skeleton-Parameter Aligned Retargeting on Humanoid Robots with Kinodynamic Trajectory Optimization

7.0

Extension

Builds On ThisRoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids

3.0

Commercially relevant

Higher ViabilityControllable Complex Human Motion Video Generation via Text-to-Skeleton Cascades

8.0

Conflicting

none indexed

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2603.15546
Route: /paper/kimodo-scaling-controllable-human-motion-generation
Active tab: read
Artifact: kimodo-scaling-controllable-human-motion-generation

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/kimodo-scaling-controllable-human-motion-generation/paper-pack
REST build passport API/api/v1/paper/kimodo-scaling-controllable-human-motion-generation/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "3fdb28dc-92c8-47fb-a663-5c42cb8920c1",
  "arxiv_id": "2603.15546",
  "canonical_route": "/paper/kimodo-scaling-controllable-human-motion-generation",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "kimodo-scaling-controllable-human-motion-generation",
  "endpoints": {
    "paper_pack": "/api/v1/paper/kimodo-scaling-controllable-human-motion-generation/paper-pack",
    "build_passport": "/api/v1/paper/kimodo-scaling-controllable-human-motion-generation/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/kimodo-scaling-controllable-human-motion-generation

stale

Proof freshness: stale
Proof status: partial
Display score: 7/10
Last proof check: 2026-03-18
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 50%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

Kimodo: Scaling Controllable Human Motion Generation

Canonical ID kimodo-scaling-controllable-human-motion-generation | Route /paper/kimodo-scaling-controllable-human-motion-generation

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/kimodo-scaling-controllable-human-motion-generation

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2603.15546"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Kimodo: Scaling Controllable Human Motion Generation",
  "normalized_query": "2603.15546",
  "route": "/paper/kimodo-scaling-controllable-human-motion-generation",
  "paper_ref": "kimodo-scaling-controllable-human-motion-generation",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Ready for execution: Kimodo: Scaling Controllable Human Motion Generation

/buildability/kimodo-scaling-controllable-human-motion-generation

Build Nowready

Subject: Kimodo: Scaling Controllable Human Motion Generation

Verdict

Build Now

Verdict is Build Now because viability and implementation proof cleared the Wave 1 scaffold thresholds.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/kimodo-scaling-controllable-human-motion-generation

Paper ref

kimodo-scaling-controllable-human-motion-generation

arXiv id

2603.15546

Freshness

Generated at

2026-03-18T22:54:37.592Z

Evidence freshness

stale

Last verification

2026-03-18T22:54:37.592Z

Sources

References

Coverage

50%

Hash state

Lineage hash

9c6bb9f5c88dcba998d3ddadec7f95ffb444f86e0351695c3cbd53cc94b93b92

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: references
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet

Verification pending / evidence receipt incomplete

references

distribution_readiness_scores

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/kimodo-scaling-controllable-human-motion-generation#webpage",
      "url": "https://sciencetostartup.com/paper/kimodo-scaling-controllable-human-motion-generation",
      "name": "Kimodo: Scaling Controllable Human Motion Generation",
      "description": "Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/kimodo-scaling-controllable-human-motion-generation#scholarlyArticle",
      "headline": "Kimodo: Scaling Controllable Human Motion Generation",
      "description": "Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.",
      "url": "https://sciencetostartup.com/paper/kimodo-scaling-controllable-human-motion-generation",
      "sameAs": "https://arxiv.org/abs/2603.15546",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2603.15546"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-03-16T17:09:30.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "54e44b45790f789c6b9593cea708b7db1d43a4c7"
          },
          "url": "https://www.semanticscholar.org/paper/54e44b45790f789c6b9593cea708b7db1d43a4c7"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "8b7471fa36abcac13a610e520de95a038e507417"
          },
          "url": "https://www.semanticscholar.org/paper/8b7471fa36abcac13a610e520de95a038e507417"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "13b83398bbe64954d8e49e1102118870753c161f"
          },
          "url": "https://www.semanticscholar.org/paper/13b83398bbe64954d8e49e1102118870753c161f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "286a2faf1f044447286778239e045cb58f9d28fb"
          },
          "url": "https://www.semanticscholar.org/paper/286a2faf1f044447286778239e045cb58f9d28fb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f787c224d28673a7d8e4987df2943a8759019b4c"
          },
          "url": "https://www.semanticscholar.org/paper/f787c224d28673a7d8e4987df2943a8759019b4c"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d0f41f728f16a0450bebc38b67a5173102d75cd5"
          },
          "url": "https://www.semanticscholar.org/paper/d0f41f728f16a0450bebc38b67a5173102d75cd5"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7d85e5a61a5d877f287e2539192e2dbfb5852541"
          },
          "url": "https://www.semanticscholar.org/paper/7d85e5a61a5d877f287e2539192e2dbfb5852541"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ca443af091e2ca9ba1aa57be10aa63ee829dacbd"
          },
          "url": "https://www.semanticscholar.org/paper/ca443af091e2ca9ba1aa57be10aa63ee829dacbd"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "03f55635c685c1cf1cae19e176a15bebb9041439"
          },
          "url": "https://www.semanticscholar.org/paper/03f55635c685c1cf1cae19e176a15bebb9041439"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7fa8382a53b62f094cbcf4ebb5315bbaf425bb86"
          },
          "url": "https://www.semanticscholar.org/paper/7fa8382a53b62f094cbcf4ebb5315bbaf425bb86"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "fe1cf34f0f2dfcac81ab9d9f4c47ae8495cbb115"
          },
          "url": "https://www.semanticscholar.org/paper/fe1cf34f0f2dfcac81ab9d9f4c47ae8495cbb115"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0c5dd68293bc1cc790e5925810d2a2e146fc90be"
          },
          "url": "https://www.semanticscholar.org/paper/0c5dd68293bc1cc790e5925810d2a2e146fc90be"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ed2fd4a9efee1e379cadc31410aa3eaa804b10c4"
          },
          "url": "https://www.semanticscholar.org/paper/ed2fd4a9efee1e379cadc31410aa3eaa804b10c4"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "5e669e2a900d124d96f7128955e9e5122130d96f"
          },
          "url": "https://www.semanticscholar.org/paper/5e669e2a900d124d96f7128955e9e5122130d96f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "04c24e80c137cd0694a86f94634ba0db207d7831"
          },
          "url": "https://www.semanticscholar.org/paper/04c24e80c137cd0694a86f94634ba0db207d7831"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f108f5d248c7af575c524d2ad2c3e90169f88add"
          },
          "url": "https://www.semanticscholar.org/paper/f108f5d248c7af575c524d2ad2c3e90169f88add"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "18594d3f15b39385bace39657d14f0c8c7479db1"
          },
          "url": "https://www.semanticscholar.org/paper/18594d3f15b39385bace39657d14f0c8c7479db1"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0f170ef970b4febb9115b5b142123cce5a1c6396"
          },
          "url": "https://www.semanticscholar.org/paper/0f170ef970b4febb9115b5b142123cce5a1c6396"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "29655c10a041bcbdf7e039c8eca9675cc62213b6"
          },
          "url": "https://www.semanticscholar.org/paper/29655c10a041bcbdf7e039c8eca9675cc62213b6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "f52af2c0cf521b48edd50670e9ba9cd02646d2b4"
          },
          "url": "https://www.semanticscholar.org/paper/f52af2c0cf521b48edd50670e9ba9cd02646d2b4"
        }
      ],
      "codeRepository": "https://github.com/nv-tlabs/kimodo",
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 7
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Human Motion Generation"
        }
      ]
    },
    {
      "@type": "SoftwareSourceCode",
      "@id": "https://sciencetostartup.com/paper/kimodo-scaling-controllable-human-motion-generation#software",
      "name": "Kimodo: Scaling Controllable Human Motion Generation - Source Code",
      "description": "Kimodo is a controllable motion generation model that synthesizes high-quality human motion from intuitive inputs.",
      "codeRepository": "https://github.com/nv-tlabs/kimodo",
      "url": "https://github.com/nv-tlabs/kimodo"
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Human Motion Generation",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Kimodo: Scaling Controllable Human Motion Generation",
          "item": "https://sciencetostartup.com/paper/kimodo-scaling-controllable-human-motion-generation"
        }
      ]
    },
    {
      "@type": "FAQPage",
      "mainEntity": [
        {
          "@type": "Question",
          "name": "What products could be built from this research?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "Now is the ideal time because demand for realistic digital humans is surging in gaming, metaverse applications, and AI-driven robotics, while advances in diffusion models and increased availability of large-scale mocap data make this technically feasible. The market is ripe for tools that bridge the gap between high cost and scalability, especially as industries push for more immersive and interactive content."
          }
        },
        {
          "@type": "Question",
          "name": "What are the practical use cases?",
          "acceptedAnswer": {
            "@type": "Answer",
            "text": "A video game studio uses the product to generate realistic NPC animations for an open-world game, inputting text prompts like 'sneaking through a forest' or kinematic constraints for specific combat moves, reducing animation production time by 70% compared to manual keyframing or limited mocap libraries."
          }
        }
      ]
    }
  ]
}

Kimodo: Scaling Controllable Human Motion Generation

Kimodo: Scaling Controllable Human Motion Generation

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(49)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(49)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline